
import numpy as np
import pandas as pd


df = pd.DataFrame({'A':[1,2,np.nan],
                  'B':[5,np.nan,np.nan],
                  'C':[1,2,3]})

df


import numpy as np
df[df.eq(0)] = np.nan
df


df.dropna()


df.dropna(axis=1)


df.dropna(thresh=2)


df.fillna(value='FILL VALUE')


df['A'].fillna(value=df['A'].mean())

0    1.0
1    2.0
2    1.5
Name: A, dtype: float64


dummy_df = pd.read_csv('dummy_data.csv')


dummy_df


dummy_df.describe()


len(dummy_df)

9


string_dummy_df = pd.read_csv('dummy_str_data.csv',index_col=0)


dummy_df.isna()


dummy_df.notna()


dummy_df.isnull()


dummy_df.isnull().sum()

Sno           0
Name          0
Age           3
Height(cm)    2
dtype: int64


string_dummy_df = pd.read_csv('dummy_str_data.csv', index_col=0)


string_dummy_df


time_df = pd.read_csv('dummy_time.csv', index_col=0)


time_df


type(time_df['birthday'][0])

str


time_df['birthday'] = pd.to_datetime(time_df['birthday'])


time_df


import pandas as pd
import numpy as np


from numpy.random import randn
np.random.seed(101)


df = pd.DataFrame(randn(5,4),index='A B C D E'.split(),columns='W X Y Z'.split())
df


pd.DataFrame(randn(5,4))

df


df['W']

A    2.706850
B    0.651118
C   -2.018168
D    0.188695
E    0.190794
Name: W, dtype: float64


# Pass a list of column names
df[['W','Z']]


# SQL Syntax (NOT RECOMMENDED!)
df.W

A    2.706850
B    0.651118
C   -2.018168
D    0.188695
E    0.190794
Name: W, dtype: float64


type(df['W'])

pandas.core.series.Series


df['new'] = df['W'] + df['Y']

df


df.drop('new',axis=1)


# Not inplace unless specified!
df


df.drop('new',axis=1,inplace=True)

df


df.drop('E',axis=0)


df.loc['A']

W    2.706850
X    0.628133
Y    0.907969
Z    0.503826
Name: A, dtype: float64


df.loc['C']

W   -2.018168
X    0.740122
Y    0.528813
Z   -0.589001
Name: C, dtype: float64


df.iloc[2]  #uporertar motoi

W   -2.018168
X    0.740122
Y    0.528813
Z   -0.589001
Name: C, dtype: float64


df.loc['B','Y']

-0.8480769834036315


df.loc[['A','B'],['W','Y']]

df


df>0


df[df>0]


df[df['W']>0]


df[df['W']>0]['Y']

A    0.907969
B   -0.848077
D   -0.933237
E    2.605967
Name: Y, dtype: float64


df[df['W']>0][['Y','X']]


df[(df['W']>0) & (df['Y'] > 1)]

df


# Reset to default 0,1...n index
df.reset_index()


newind = 'CA NY WY OR CO'.split()


df['States'] = newind

df


df.set_index('States')

df


df.set_index('States',inplace=True)

df


# Index Levels
outside = ['G1','G1','G1','G2','G2','G2']
inside = [1,2,3,1,2,3]
hier_index = list(zip(outside,inside))
hier_index = pd.MultiIndex.from_tuples(hier_index)


hier_index

MultiIndex([('G1', 1),
            ('G1', 2),
            ('G1', 3),
            ('G2', 1),
            ('G2', 2),
            ('G2', 3)],
           )


df = pd.DataFrame(np.random.randn(6,2),index=hier_index,columns=['A','B'])
df


df.loc['G1']


df.loc['G1'].loc[1]

A   -0.993263
B    0.196800
Name: 1, dtype: float64


df.index.names

FrozenList([None, None])


df.index.names = ['Group','Num']

df


df.xs('G1')


df.xs(['G1',1])

A   -0.993263
B    0.196800
Name: (G1, 1), dtype: float64


df.xs(1,level='Num')


import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt


# First argument is mean
# Second argument is standard deviation
# Third argument is size
x = np.random.normal(50, 5, 3000)

x

array([45.27774055, 49.99545773, 54.67905363, ..., 45.46887562,
       49.03996203, 44.89792021])


print("Max is {}".format(max(x)))
print("Min is {}".format(min(x)))
print("Max - Min is {}".format(max(x) - min(x)))

Max is 68.56357483500099
Min is 32.13656656048891
Max - Min is 36.42700827451208


sns.distplot(x, kde=False, bins=5,
             hist_kws=dict(edgecolor="k", linewidth=2))
plt.xlabel('Intervals')
plt.ylabel('Frequency')
plt.show()


sns.distplot(x, kde=False, bins=10, hist_kws=dict(edgecolor="k", linewidth=2))
plt.xlabel('Intervals')
plt.ylabel('Frequency')
plt.show()


sns.distplot(x, kde=False, bins=15, hist_kws=dict(edgecolor="k", linewidth=2))
plt.xlabel('Intervals')
plt.ylabel('Frequency')
plt.show()


sns.distplot(x, kde=False, bins=50, hist_kws=dict(edgecolor="k", linewidth=2))
plt.xlabel('Intervals')
plt.ylabel('Frequency')
plt.show()


sns.distplot(x, kde=False, bins=30, hist_kws=dict(edgecolor="k", linewidth=2))
plt.xlabel('Intervals')
plt.ylabel('Frequency')
plt.show()


sns.distplot(x, kde=False, bins=30,
             norm_hist=True,
             hist_kws=dict(edgecolor="k", linewidth=2))
plt.xlabel('Intervals')
plt.ylabel('Relative Frequency')
plt.show()


sns.distplot(x, kde=True, bins=30,
             norm_hist=True,
             hist_kws=dict(edgecolor="r", linewidth=2))
plt.xticks(range(28, 70, 4))
plt.ylabel('Density')
plt.show()

/home/kashif/anaconda3/lib/python3.7/site-packages/scipy/stats/stats.py:1713: FutureWarning: Using a non-tuple sequence for multidimensional indexing is deprecated; use `arr[tuple(seq)]` instead of `arr[seq]`. In the future this will be interpreted as an array index, `arr[np.array(seq)]`, which will result either in an error or a different result.
  return np.add.reduce(sorted[indexer] * weights, axis=axis) / sumval


plt.axvline(x.mean(), color='b', linestyle='dashed', linewidth=1)
plt.axvline(np.median(x), color='r', linestyle='dashed', linewidth=4)
sns.distplot(x, kde=True, bins=30, hist=False)
plt.ylabel('Density')
plt.show()


np.median(x)

49.99594390121429


np.mean(x)

50.0234060825881


import pandas as pd
import numpy as np


dummy_df = pd.read_csv('dummy_data.csv')


dummy_df


dummy_df.describe()


len(dummy_df)

9


string_dummy_df = pd.read_csv('dummy_str_data.csv',index_col=0)


dummy_df.isna()


dummy_df.notna()


dummy_df.isnull()


dummy_df.isnull().sum()

Sno           0
Name          0
Age           3
Height(cm)    2
dtype: int64


string_dummy_df = pd.read_csv('dummy_str_data.csv', index_col=0)


string_dummy_df


time_df = pd.read_csv('dummy_time.csv', index_col=0)


time_df


type(time_df['birthday'][0])

str


time_df['birthday'] = pd.to_datetime(time_df['birthday'])


time_df


import numpy as np
import scipy.stats
import pandas as pd


dummy_age = [20, 21, 24, 24, 28, 26, 19, 22, 26, 24, 21,
            19, 22, 28, 29, 6, 100, 25, 25, 28, 31]
dummy_height = [150, 151, 155, 153, 280, 160, 158, 157, 158, 145, 150,
               155, 155, 151, 152, 153, 160, 152, 157, 157, 160, 153]
dummy_df = pd.DataFrame(list(zip(dummy_age, dummy_height)),
                        columns =['Age', 'Height(cm)'])


dummy_df


def modified_z_score(my_data):
    # First Calculate Median
    median_my_data = np.median(my_data)
    
    # Median Absolute Deviation 
    # Median of | X_i - median of X| for all X_i
    mad = np.median(my_data.map(lambda x: np.abs(x - median_my_data)))
    
    # Modified Z score
    # 0.6745 * (X_i - median of X)/Median Absolute Deviation
    modified_z_score = list(my_data.map(lambda x: 0.6745* (x - median_my_data)/mad))
    return modified_z_score


modified_z_score(dummy_df['Age'])

[-0.8993333333333333,
 -0.6745,
 0.0,
 0.0,
 0.8993333333333333,
 0.44966666666666666,
 -1.1241666666666668,
 -0.44966666666666666,
 0.44966666666666666,
 0.0,
 -0.6745,
 -1.1241666666666668,
 -0.44966666666666666,
 0.8993333333333333,
 1.1241666666666668,
 -4.047,
 17.087333333333333,
 0.22483333333333333,
 0.22483333333333333,
 0.8993333333333333,
 1.5738333333333332]


mod_z_score_age = modified_z_score(dummy_df['Age'])
dummy_df.iloc[np.where(np.abs(mod_z_score_height)>=3)]


mod_z_score_height = modified_z_score(dummy_df['Height(cm)'])
dummy_df.iloc[np.where(np.abs(mod_z_score_height)>=3)]


import pandas as pd
df = pd.read_csv('titanic-data.csv', index_col=0)


df.head()


df.describe()


df.columns

Index(['Survived', 'Pclass', 'Name', 'Sex', 'Age', 'SibSp', 'Parch', 'Ticket',
       'Fare', 'Cabin', 'Embarked'],
      dtype='object')


df['Age']

PassengerId
1      22.0
2      38.0
3      26.0
4      35.0
5      35.0
6       NaN
7      54.0
8       2.0
9      27.0
10     14.0
11      4.0
12     58.0
13     20.0
14     39.0
15     14.0
16     55.0
17      2.0
18      NaN
19     31.0
20      NaN
21     35.0
22     34.0
23     15.0
24     28.0
25      8.0
26     38.0
27      NaN
28     19.0
29      NaN
30      NaN
       ... 
862    21.0
863    48.0
864     NaN
865    24.0
866    42.0
867    27.0
868    31.0
869     NaN
870     4.0
871    26.0
872    47.0
873    33.0
874    47.0
875    28.0
876    15.0
877    20.0
878    19.0
879     NaN
880    56.0
881    25.0
882    33.0
883    22.0
884    28.0
885    25.0
886    39.0
887    27.0
888    19.0
889     NaN
890    26.0
891    32.0
Name: Age, Length: 891, dtype: float64


# It does not make sense to use unique
df['Age'].unique()

array([22.  , 38.  , 26.  , 35.  ,   nan, 54.  ,  2.  , 27.  , 14.  ,
        4.  , 58.  , 20.  , 39.  , 55.  , 31.  , 34.  , 15.  , 28.  ,
        8.  , 19.  , 40.  , 66.  , 42.  , 21.  , 18.  ,  3.  ,  7.  ,
       49.  , 29.  , 65.  , 28.5 ,  5.  , 11.  , 45.  , 17.  , 32.  ,
       16.  , 25.  ,  0.83, 30.  , 33.  , 23.  , 24.  , 46.  , 59.  ,
       71.  , 37.  , 47.  , 14.5 , 70.5 , 32.5 , 12.  ,  9.  , 36.5 ,
       51.  , 55.5 , 40.5 , 44.  ,  1.  , 61.  , 56.  , 50.  , 36.  ,
       45.5 , 20.5 , 62.  , 41.  , 52.  , 63.  , 23.5 ,  0.92, 43.  ,
       60.  , 10.  , 64.  , 13.  , 48.  ,  0.75, 53.  , 57.  , 80.  ,
       70.  , 24.5 ,  6.  ,  0.67, 30.5 ,  0.42, 34.5 , 74.  ])


df['Fare']

PassengerId
1        7.2500
2       71.2833
3        7.9250
4       53.1000
5        8.0500
6        8.4583
7       51.8625
8       21.0750
9       11.1333
10      30.0708
11      16.7000
12      26.5500
13       8.0500
14      31.2750
15       7.8542
16      16.0000
17      29.1250
18      13.0000
19      18.0000
20       7.2250
21      26.0000
22      13.0000
23       8.0292
24      35.5000
25      21.0750
26      31.3875
27       7.2250
28     263.0000
29       7.8792
30       7.8958
         ...   
862     11.5000
863     25.9292
864     69.5500
865     13.0000
866     13.0000
867     13.8583
868     50.4958
869      9.5000
870     11.1333
871      7.8958
872     52.5542
873      5.0000
874      9.0000
875     24.0000
876      7.2250
877      9.8458
878      7.8958
879      7.8958
880     83.1583
881     26.0000
882      7.8958
883     10.5167
884     10.5000
885      7.0500
886     29.1250
887     13.0000
888     30.0000
889     23.4500
890     30.0000
891      7.7500
Name: Fare, Length: 891, dtype: float64


df['SibSp']

PassengerId
1      1
2      1
3      0
4      1
5      0
6      0
7      0
8      3
9      0
10     1
11     1
12     0
13     0
14     1
15     0
16     0
17     4
18     0
19     1
20     0
21     0
22     0
23     0
24     0
25     3
26     1
27     0
28     3
29     0
30     0
      ..
862    1
863    0
864    8
865    0
866    0
867    1
868    0
869    0
870    1
871    0
872    1
873    0
874    0
875    1
876    0
877    0
878    0
879    0
880    0
881    0
882    0
883    0
884    0
885    0
886    0
887    0
888    0
889    1
890    0
891    0
Name: SibSp, Length: 891, dtype: int64


df['SibSp'].unique()

array([1, 0, 3, 4, 2, 5, 8])


df['Parch'].unique()

array([0, 1, 2, 5, 3, 4, 6])


df['Sex'].unique()

array(['male', 'female'], dtype=object)


# it does not make sense to use unique on Name
df['Name'].unique()

array(['Braund, Mr. Owen Harris',
       'Cumings, Mrs. John Bradley (Florence Briggs Thayer)',
       'Heikkinen, Miss. Laina',
       'Futrelle, Mrs. Jacques Heath (Lily May Peel)',
       'Allen, Mr. William Henry', 'Moran, Mr. James',
       'McCarthy, Mr. Timothy J', 'Palsson, Master. Gosta Leonard',
       'Johnson, Mrs. Oscar W (Elisabeth Vilhelmina Berg)',
       'Nasser, Mrs. Nicholas (Adele Achem)',
       'Sandstrom, Miss. Marguerite Rut', 'Bonnell, Miss. Elizabeth',
       'Saundercock, Mr. William Henry', 'Andersson, Mr. Anders Johan',
       'Vestrom, Miss. Hulda Amanda Adolfina',
       'Hewlett, Mrs. (Mary D Kingcome) ', 'Rice, Master. Eugene',
       'Williams, Mr. Charles Eugene',
       'Vander Planke, Mrs. Julius (Emelia Maria Vandemoortele)',
       'Masselmani, Mrs. Fatima', 'Fynney, Mr. Joseph J',
       'Beesley, Mr. Lawrence', 'McGowan, Miss. Anna "Annie"',
       'Sloper, Mr. William Thompson', 'Palsson, Miss. Torborg Danira',
       'Asplund, Mrs. Carl Oscar (Selma Augusta Emilia Johansson)',
       'Emir, Mr. Farred Chehab', 'Fortune, Mr. Charles Alexander',
       'O\'Dwyer, Miss. Ellen "Nellie"', 'Todoroff, Mr. Lalio',
       'Uruchurtu, Don. Manuel E',
       'Spencer, Mrs. William Augustus (Marie Eugenie)',
       'Glynn, Miss. Mary Agatha', 'Wheadon, Mr. Edward H',
       'Meyer, Mr. Edgar Joseph', 'Holverson, Mr. Alexander Oskar',
       'Mamee, Mr. Hanna', 'Cann, Mr. Ernest Charles',
       'Vander Planke, Miss. Augusta Maria',
       'Nicola-Yarred, Miss. Jamila',
       'Ahlin, Mrs. Johan (Johanna Persdotter Larsson)',
       'Turpin, Mrs. William John Robert (Dorothy Ann Wonnacott)',
       'Kraeff, Mr. Theodor', 'Laroche, Miss. Simonne Marie Anne Andree',
       'Devaney, Miss. Margaret Delia', 'Rogers, Mr. William John',
       'Lennon, Mr. Denis', "O'Driscoll, Miss. Bridget",
       'Samaan, Mr. Youssef',
       'Arnold-Franchi, Mrs. Josef (Josefine Franchi)',
       'Panula, Master. Juha Niilo', 'Nosworthy, Mr. Richard Cater',
       'Harper, Mrs. Henry Sleeper (Myna Haxtun)',
       'Faunthorpe, Mrs. Lizzie (Elizabeth Anne Wilkinson)',
       'Ostby, Mr. Engelhart Cornelius', 'Woolner, Mr. Hugh',
       'Rugg, Miss. Emily', 'Novel, Mr. Mansouer',
       'West, Miss. Constance Mirium',
       'Goodwin, Master. William Frederick', 'Sirayanian, Mr. Orsen',
       'Icard, Miss. Amelie', 'Harris, Mr. Henry Birkhardt',
       'Skoog, Master. Harald', 'Stewart, Mr. Albert A',
       'Moubarek, Master. Gerios', 'Nye, Mrs. (Elizabeth Ramell)',
       'Crease, Mr. Ernest James', 'Andersson, Miss. Erna Alexandra',
       'Kink, Mr. Vincenz', 'Jenkin, Mr. Stephen Curnow',
       'Goodwin, Miss. Lillian Amy', 'Hood, Mr. Ambrose Jr',
       'Chronopoulos, Mr. Apostolos', 'Bing, Mr. Lee',
       'Moen, Mr. Sigurd Hansen', 'Staneff, Mr. Ivan',
       'Moutal, Mr. Rahamin Haim', 'Caldwell, Master. Alden Gates',
       'Dowdell, Miss. Elizabeth', 'Waelens, Mr. Achille',
       'Sheerlinck, Mr. Jan Baptist', 'McDermott, Miss. Brigdet Delia',
       'Carrau, Mr. Francisco M', 'Ilett, Miss. Bertha',
       'Backstrom, Mrs. Karl Alfred (Maria Mathilda Gustafsson)',
       'Ford, Mr. William Neal', 'Slocovski, Mr. Selman Francis',
       'Fortune, Miss. Mabel Helen', 'Celotti, Mr. Francesco',
       'Christmann, Mr. Emil', 'Andreasson, Mr. Paul Edvin',
       'Chaffee, Mr. Herbert Fuller', 'Dean, Mr. Bertram Frank',
       'Coxon, Mr. Daniel', 'Shorney, Mr. Charles Joseph',
       'Goldschmidt, Mr. George B', 'Greenfield, Mr. William Bertram',
       'Doling, Mrs. John T (Ada Julia Bone)', 'Kantor, Mr. Sinai',
       'Petranec, Miss. Matilda', 'Petroff, Mr. Pastcho ("Pentcho")',
       'White, Mr. Richard Frasar', 'Johansson, Mr. Gustaf Joel',
       'Gustafsson, Mr. Anders Vilhelm', 'Mionoff, Mr. Stoytcho',
       'Salkjelsvik, Miss. Anna Kristine', 'Moss, Mr. Albert Johan',
       'Rekic, Mr. Tido', 'Moran, Miss. Bertha',
       'Porter, Mr. Walter Chamberlain', 'Zabour, Miss. Hileni',
       'Barton, Mr. David John', 'Jussila, Miss. Katriina',
       'Attalah, Miss. Malake', 'Pekoniemi, Mr. Edvard',
       'Connors, Mr. Patrick', 'Turpin, Mr. William John Robert',
       'Baxter, Mr. Quigg Edmond', 'Andersson, Miss. Ellis Anna Maria',
       'Hickman, Mr. Stanley George', 'Moore, Mr. Leonard Charles',
       'Nasser, Mr. Nicholas', 'Webber, Miss. Susan',
       'White, Mr. Percival Wayland', 'Nicola-Yarred, Master. Elias',
       'McMahon, Mr. Martin', 'Madsen, Mr. Fridtjof Arne',
       'Peter, Miss. Anna', 'Ekstrom, Mr. Johan', 'Drazenoic, Mr. Jozef',
       'Coelho, Mr. Domingos Fernandeo',
       'Robins, Mrs. Alexander A (Grace Charity Laury)',
       'Weisz, Mrs. Leopold (Mathilde Francoise Pede)',
       'Sobey, Mr. Samuel James Hayden', 'Richard, Mr. Emile',
       'Newsom, Miss. Helen Monypeny', 'Futrelle, Mr. Jacques Heath',
       'Osen, Mr. Olaf Elon', 'Giglio, Mr. Victor',
       'Boulos, Mrs. Joseph (Sultana)', 'Nysten, Miss. Anna Sofia',
       'Hakkarainen, Mrs. Pekka Pietari (Elin Matilda Dolck)',
       'Burke, Mr. Jeremiah', 'Andrew, Mr. Edgardo Samuel',
       'Nicholls, Mr. Joseph Charles',
       'Andersson, Mr. August Edvard ("Wennerstrom")',
       'Ford, Miss. Robina Maggie "Ruby"',
       'Navratil, Mr. Michel ("Louis M Hoffman")',
       'Byles, Rev. Thomas Roussel Davids', 'Bateman, Rev. Robert James',
       'Pears, Mrs. Thomas (Edith Wearne)', 'Meo, Mr. Alfonzo',
       'van Billiard, Mr. Austin Blyler', 'Olsen, Mr. Ole Martin',
       'Williams, Mr. Charles Duane', 'Gilnagh, Miss. Katherine "Katie"',
       'Corn, Mr. Harry', 'Smiljanic, Mr. Mile',
       'Sage, Master. Thomas Henry', 'Cribb, Mr. John Hatfield',
       'Watt, Mrs. James (Elizabeth "Bessie" Inglis Milne)',
       'Bengtsson, Mr. John Viktor', 'Calic, Mr. Jovo',
       'Panula, Master. Eino Viljami',
       'Goldsmith, Master. Frank John William "Frankie"',
       'Chibnall, Mrs. (Edith Martha Bowerman)',
       'Skoog, Mrs. William (Anna Bernhardina Karlsson)',
       'Baumann, Mr. John D', 'Ling, Mr. Lee',
       'Van der hoef, Mr. Wyckoff', 'Rice, Master. Arthur',
       'Johnson, Miss. Eleanor Ileen', 'Sivola, Mr. Antti Wilhelm',
       'Smith, Mr. James Clinch', 'Klasen, Mr. Klas Albin',
       'Lefebre, Master. Henry Forbes', 'Isham, Miss. Ann Elizabeth',
       'Hale, Mr. Reginald', 'Leonard, Mr. Lionel',
       'Sage, Miss. Constance Gladys', 'Pernot, Mr. Rene',
       'Asplund, Master. Clarence Gustaf Hugo',
       'Becker, Master. Richard F', 'Kink-Heilmann, Miss. Luise Gretchen',
       'Rood, Mr. Hugh Roscoe',
       'O\'Brien, Mrs. Thomas (Johanna "Hannah" Godfrey)',
       'Romaine, Mr. Charles Hallace ("Mr C Rolmane")',
       'Bourke, Mr. John', 'Turcin, Mr. Stjepan', 'Pinsky, Mrs. (Rosa)',
       'Carbines, Mr. William',
       'Andersen-Jensen, Miss. Carla Christine Nielsine',
       'Navratil, Master. Michel M',
       'Brown, Mrs. James Joseph (Margaret Tobin)',
       'Lurette, Miss. Elise', 'Mernagh, Mr. Robert',
       'Olsen, Mr. Karl Siegwart Andreas',
       'Madigan, Miss. Margaret "Maggie"',
       'Yrois, Miss. Henriette ("Mrs Harbeck")',
       'Vande Walle, Mr. Nestor Cyriel', 'Sage, Mr. Frederick',
       'Johanson, Mr. Jakob Alfred', 'Youseff, Mr. Gerious',
       'Cohen, Mr. Gurshon "Gus"', 'Strom, Miss. Telma Matilda',
       'Backstrom, Mr. Karl Alfred', 'Albimona, Mr. Nassef Cassem',
       'Carr, Miss. Helen "Ellen"', 'Blank, Mr. Henry', 'Ali, Mr. Ahmed',
       'Cameron, Miss. Clear Annie', 'Perkin, Mr. John Henry',
       'Givard, Mr. Hans Kristensen', 'Kiernan, Mr. Philip',
       'Newell, Miss. Madeleine', 'Honkanen, Miss. Eliina',
       'Jacobsohn, Mr. Sidney Samuel', 'Bazzani, Miss. Albina',
       'Harris, Mr. Walter', 'Sunderland, Mr. Victor Francis',
       'Bracken, Mr. James H', 'Green, Mr. George Henry',
       'Nenkoff, Mr. Christo', 'Hoyt, Mr. Frederick Maxfield',
       'Berglund, Mr. Karl Ivar Sven', 'Mellors, Mr. William John',
       'Lovell, Mr. John Hall ("Henry")', 'Fahlstrom, Mr. Arne Jonas',
       'Lefebre, Miss. Mathilde',
       'Harris, Mrs. Henry Birkhardt (Irene Wallach)',
       'Larsson, Mr. Bengt Edvin', 'Sjostedt, Mr. Ernst Adolf',
       'Asplund, Miss. Lillian Gertrud',
       'Leyson, Mr. Robert William Norman',
       'Harknett, Miss. Alice Phoebe', 'Hold, Mr. Stephen',
       'Collyer, Miss. Marjorie "Lottie"',
       'Pengelly, Mr. Frederick William', 'Hunt, Mr. George Henry',
       'Zabour, Miss. Thamine', 'Murphy, Miss. Katherine "Kate"',
       'Coleridge, Mr. Reginald Charles', 'Maenpaa, Mr. Matti Alexanteri',
       'Attalah, Mr. Sleiman', 'Minahan, Dr. William Edward',
       'Lindahl, Miss. Agda Thorilda Viktoria',
       'Hamalainen, Mrs. William (Anna)', 'Beckwith, Mr. Richard Leonard',
       'Carter, Rev. Ernest Courtenay', 'Reed, Mr. James George',
       'Strom, Mrs. Wilhelm (Elna Matilda Persson)',
       'Stead, Mr. William Thomas', 'Lobb, Mr. William Arthur',
       'Rosblom, Mrs. Viktor (Helena Wilhelmina)',
       'Touma, Mrs. Darwis (Hanne Youssef Razi)',
       'Thorne, Mrs. Gertrude Maybelle', 'Cherry, Miss. Gladys',
       'Ward, Miss. Anna', 'Parrish, Mrs. (Lutie Davis)',
       'Smith, Mr. Thomas', 'Asplund, Master. Edvin Rojj Felix',
       'Taussig, Mr. Emil', 'Harrison, Mr. William', 'Henry, Miss. Delia',
       'Reeves, Mr. David', 'Panula, Mr. Ernesti Arvid',
       'Persson, Mr. Ernst Ulrik',
       'Graham, Mrs. William Thompson (Edith Junkins)',
       'Bissette, Miss. Amelia', 'Cairns, Mr. Alexander',
       'Tornquist, Mr. William Henry',
       'Mellinger, Mrs. (Elizabeth Anne Maidment)',
       'Natsch, Mr. Charles H', 'Healy, Miss. Hanora "Nora"',
       'Andrews, Miss. Kornelia Theodosia',
       'Lindblom, Miss. Augusta Charlotta', 'Parkes, Mr. Francis "Frank"',
       'Rice, Master. Eric', 'Abbott, Mrs. Stanton (Rosa Hunt)',
       'Duane, Mr. Frank', 'Olsson, Mr. Nils Johan Goransson',
       'de Pelsmaeker, Mr. Alfons', 'Dorking, Mr. Edward Arthur',
       'Smith, Mr. Richard William', 'Stankovic, Mr. Ivan',
       'de Mulder, Mr. Theodore', 'Naidenoff, Mr. Penko',
       'Hosono, Mr. Masabumi', 'Connolly, Miss. Kate',
       'Barber, Miss. Ellen "Nellie"',
       'Bishop, Mrs. Dickinson H (Helen Walton)',
       'Levy, Mr. Rene Jacques', 'Haas, Miss. Aloisia',
       'Mineff, Mr. Ivan', 'Lewy, Mr. Ervin G', 'Hanna, Mr. Mansour',
       'Allison, Miss. Helen Loraine', 'Saalfeld, Mr. Adolphe',
       'Baxter, Mrs. James (Helene DeLaudeniere Chaput)',
       'Kelly, Miss. Anna Katherine "Annie Kate"', 'McCoy, Mr. Bernard',
       'Johnson, Mr. William Cahoone Jr', 'Keane, Miss. Nora A',
       'Williams, Mr. Howard Hugh "Harry"',
       'Allison, Master. Hudson Trevor', 'Fleming, Miss. Margaret',
       'Penasco y Castellana, Mrs. Victor de Satode (Maria Josefa Perez de Soto y Vallejo)',
       'Abelson, Mr. Samuel', 'Francatelli, Miss. Laura Mabel',
       'Hays, Miss. Margaret Bechstein', 'Ryerson, Miss. Emily Borie',
       'Lahtinen, Mrs. William (Anna Sylfven)', 'Hendekovic, Mr. Ignjac',
       'Hart, Mr. Benjamin', 'Nilsson, Miss. Helmina Josefina',
       'Kantor, Mrs. Sinai (Miriam Sternin)', 'Moraweck, Dr. Ernest',
       'Wick, Miss. Mary Natalie',
       'Spedden, Mrs. Frederic Oakley (Margaretta Corning Stone)',
       'Dennis, Mr. Samuel', 'Danoff, Mr. Yoto',
       'Slayter, Miss. Hilda Mary',
       'Caldwell, Mrs. Albert Francis (Sylvia Mae Harbaugh)',
       'Sage, Mr. George John Jr', 'Young, Miss. Marie Grice',
       'Nysveen, Mr. Johan Hansen', 'Ball, Mrs. (Ada E Hall)',
       'Goldsmith, Mrs. Frank John (Emily Alice Brown)',
       'Hippach, Miss. Jean Gertrude', 'McCoy, Miss. Agnes',
       'Partner, Mr. Austen', 'Graham, Mr. George Edward',
       'Vander Planke, Mr. Leo Edmondus',
       'Frauenthal, Mrs. Henry William (Clara Heinsheimer)',
       'Denkoff, Mr. Mitto', 'Pears, Mr. Thomas Clinton',
       'Burns, Miss. Elizabeth Margaret', 'Dahl, Mr. Karl Edwart',
       'Blackwell, Mr. Stephen Weart', 'Navratil, Master. Edmond Roger',
       'Fortune, Miss. Alice Elizabeth', 'Collander, Mr. Erik Gustaf',
       'Sedgwick, Mr. Charles Frederick Waddington',
       'Fox, Mr. Stanley Hubert', 'Brown, Miss. Amelia "Mildred"',
       'Smith, Miss. Marion Elsie',
       'Davison, Mrs. Thomas Henry (Mary E Finck)',
       'Coutts, Master. William Loch "William"', 'Dimic, Mr. Jovan',
       'Odahl, Mr. Nils Martin', 'Williams-Lambert, Mr. Fletcher Fellows',
       'Elias, Mr. Tannous', 'Arnold-Franchi, Mr. Josef',
       'Yousif, Mr. Wazli', 'Vanden Steen, Mr. Leo Peter',
       'Bowerman, Miss. Elsie Edith', 'Funk, Miss. Annie Clemmer',
       'McGovern, Miss. Mary', 'Mockler, Miss. Helen Mary "Ellie"',
       'Skoog, Mr. Wilhelm', 'del Carlo, Mr. Sebastiano',
       'Barbara, Mrs. (Catherine David)', 'Asim, Mr. Adola',
       "O'Brien, Mr. Thomas", 'Adahl, Mr. Mauritz Nils Martin',
       'Warren, Mrs. Frank Manley (Anna Sophia Atkinson)',
       'Moussa, Mrs. (Mantoura Boulos)', 'Jermyn, Miss. Annie',
       'Aubart, Mme. Leontine Pauline', 'Harder, Mr. George Achilles',
       'Wiklund, Mr. Jakob Alfred', 'Beavan, Mr. William Thomas',
       'Ringhini, Mr. Sante', 'Palsson, Miss. Stina Viola',
       'Meyer, Mrs. Edgar Joseph (Leila Saks)',
       'Landergren, Miss. Aurora Adelia', 'Widener, Mr. Harry Elkins',
       'Betros, Mr. Tannous', 'Gustafsson, Mr. Karl Gideon',
       'Bidois, Miss. Rosalie', 'Nakid, Miss. Maria ("Mary")',
       'Tikkanen, Mr. Juho',
       'Holverson, Mrs. Alexander Oskar (Mary Aline Towner)',
       'Plotcharsky, Mr. Vasil', 'Davies, Mr. Charles Henry',
       'Goodwin, Master. Sidney Leonard', 'Buss, Miss. Kate',
       'Sadlier, Mr. Matthew', 'Lehmann, Miss. Bertha',
       'Carter, Mr. William Ernest', 'Jansson, Mr. Carl Olof',
       'Gustafsson, Mr. Johan Birger', 'Newell, Miss. Marjorie',
       'Sandstrom, Mrs. Hjalmar (Agnes Charlotta Bengtsson)',
       'Johansson, Mr. Erik', 'Olsson, Miss. Elina',
       'McKane, Mr. Peter David', 'Pain, Dr. Alfred',
       'Trout, Mrs. William H (Jessie L)', 'Niskanen, Mr. Juha',
       'Adams, Mr. John', 'Jussila, Miss. Mari Aina',
       'Hakkarainen, Mr. Pekka Pietari', 'Oreskovic, Miss. Marija',
       'Gale, Mr. Shadrach', 'Widegren, Mr. Carl/Charles Peter',
       'Richards, Master. William Rowe',
       'Birkeland, Mr. Hans Martin Monsen', 'Lefebre, Miss. Ida',
       'Sdycoff, Mr. Todor', 'Hart, Mr. Henry', 'Minahan, Miss. Daisy E',
       'Cunningham, Mr. Alfred Fleming', 'Sundman, Mr. Johan Julian',
       'Meek, Mrs. Thomas (Annie Louise Rowley)',
       'Drew, Mrs. James Vivian (Lulu Thorne Christian)',
       'Silven, Miss. Lyyli Karoliina', 'Matthews, Mr. William John',
       'Van Impe, Miss. Catharina', 'Gheorgheff, Mr. Stanio',
       'Charters, Mr. David', 'Zimmerman, Mr. Leo',
       'Danbom, Mrs. Ernst Gilbert (Anna Sigrid Maria Brogren)',
       'Rosblom, Mr. Viktor Richard', 'Wiseman, Mr. Phillippe',
       'Clarke, Mrs. Charles V (Ada Maria Winfield)',
       'Phillips, Miss. Kate Florence ("Mrs Kate Louise Phillips Marshall")',
       'Flynn, Mr. James', 'Pickard, Mr. Berk (Berk Trembisky)',
       'Bjornstrom-Steffansson, Mr. Mauritz Hakan',
       'Thorneycroft, Mrs. Percival (Florence Kate White)',
       'Louch, Mrs. Charles Alexander (Alice Adelaide Slow)',
       'Kallio, Mr. Nikolai Erland', 'Silvey, Mr. William Baird',
       'Carter, Miss. Lucile Polk',
       'Ford, Miss. Doolina Margaret "Daisy"',
       'Richards, Mrs. Sidney (Emily Hocking)', 'Fortune, Mr. Mark',
       'Kvillner, Mr. Johan Henrik Johannesson',
       'Hart, Mrs. Benjamin (Esther Ada Bloomfield)', 'Hampe, Mr. Leon',
       'Petterson, Mr. Johan Emil', 'Reynaldo, Ms. Encarnacion',
       'Johannesen-Bratthammer, Mr. Bernt', 'Dodge, Master. Washington',
       'Mellinger, Miss. Madeleine Violet', 'Seward, Mr. Frederic Kimber',
       'Baclini, Miss. Marie Catherine', 'Peuchen, Major. Arthur Godfrey',
       'West, Mr. Edwy Arthur', 'Hagland, Mr. Ingvald Olai Olsen',
       'Foreman, Mr. Benjamin Laventall', 'Goldenberg, Mr. Samuel L',
       'Peduzzi, Mr. Joseph', 'Jalsevac, Mr. Ivan',
       'Millet, Mr. Francis Davis', 'Kenyon, Mrs. Frederick R (Marion)',
       'Toomey, Miss. Ellen', "O'Connor, Mr. Maurice",
       'Anderson, Mr. Harry', 'Morley, Mr. William', 'Gee, Mr. Arthur H',
       'Milling, Mr. Jacob Christian', 'Maisner, Mr. Simon',
       'Goncalves, Mr. Manuel Estanslas', 'Campbell, Mr. William',
       'Smart, Mr. John Montgomery', 'Scanlan, Mr. James',
       'Baclini, Miss. Helene Barbara', 'Keefe, Mr. Arthur',
       'Cacic, Mr. Luka', 'West, Mrs. Edwy Arthur (Ada Mary Worth)',
       'Jerwan, Mrs. Amin S (Marie Marthe Thuillard)',
       'Strandberg, Miss. Ida Sofia', 'Clifford, Mr. George Quincy',
       'Renouf, Mr. Peter Henry', 'Braund, Mr. Lewis Richard',
       'Karlsson, Mr. Nils August', 'Hirvonen, Miss. Hildur E',
       'Goodwin, Master. Harold Victor',
       'Frost, Mr. Anthony Wood "Archie"', 'Rouse, Mr. Richard Henry',
       'Turkula, Mrs. (Hedwig)', 'Bishop, Mr. Dickinson H',
       'Lefebre, Miss. Jeannie',
       'Hoyt, Mrs. Frederick Maxfield (Jane Anne Forby)',
       'Kent, Mr. Edward Austin', 'Somerton, Mr. Francis William',
       'Coutts, Master. Eden Leslie "Neville"',
       'Hagland, Mr. Konrad Mathias Reiersen', 'Windelov, Mr. Einar',
       'Molson, Mr. Harry Markland', 'Artagaveytia, Mr. Ramon',
       'Stanley, Mr. Edward Roland', 'Yousseff, Mr. Gerious',
       'Eustis, Miss. Elizabeth Mussey',
       'Shellard, Mr. Frederick William',
       'Allison, Mrs. Hudson J C (Bessie Waldo Daniels)',
       'Svensson, Mr. Olof', 'Calic, Mr. Petar', 'Canavan, Miss. Mary',
       "O'Sullivan, Miss. Bridget Mary", 'Laitinen, Miss. Kristina Sofia',
       'Maioni, Miss. Roberta',
       'Penasco y Castellana, Mr. Victor de Satode',
       'Quick, Mrs. Frederick Charles (Jane Richards)',
       'Bradley, Mr. George ("George Arthur Brayton")',
       'Olsen, Mr. Henry Margido', 'Lang, Mr. Fang',
       'Daly, Mr. Eugene Patrick', 'Webber, Mr. James',
       'McGough, Mr. James Robert',
       'Rothschild, Mrs. Martin (Elizabeth L. Barrett)',
       'Coleff, Mr. Satio', 'Walker, Mr. William Anderson',
       'Lemore, Mrs. (Amelia Milley)', 'Ryan, Mr. Patrick',
       'Angle, Mrs. William A (Florence "Mary" Agnes Hughes)',
       'Pavlovic, Mr. Stefo', 'Perreault, Miss. Anne', 'Vovk, Mr. Janko',
       'Lahoud, Mr. Sarkis',
       'Hippach, Mrs. Louis Albert (Ida Sophia Fischer)',
       'Kassem, Mr. Fared', 'Farrell, Mr. James', 'Ridsdale, Miss. Lucy',
       'Farthing, Mr. John', 'Salonen, Mr. Johan Werner',
       'Hocking, Mr. Richard George', 'Quick, Miss. Phyllis May',
       'Toufik, Mr. Nakli', 'Elias, Mr. Joseph Jr',
       'Peter, Mrs. Catherine (Catherine Rizk)', 'Cacic, Miss. Marija',
       'Hart, Miss. Eva Miriam', 'Butt, Major. Archibald Willingham',
       'LeRoy, Miss. Bertha', 'Risien, Mr. Samuel Beard',
       'Frolicher, Miss. Hedwig Margaritha', 'Crosby, Miss. Harriet R',
       'Andersson, Miss. Ingeborg Constanzia',
       'Andersson, Miss. Sigrid Elisabeth', 'Beane, Mr. Edward',
       'Douglas, Mr. Walter Donald', 'Nicholson, Mr. Arthur Ernest',
       'Beane, Mrs. Edward (Ethel Clarke)', 'Padro y Manent, Mr. Julian',
       'Goldsmith, Mr. Frank John', 'Davies, Master. John Morgan Jr',
       'Thayer, Mr. John Borland Jr', 'Sharp, Mr. Percival James R',
       "O'Brien, Mr. Timothy", 'Leeni, Mr. Fahim ("Philip Zenni")',
       'Ohman, Miss. Velin', 'Wright, Mr. George',
       'Duff Gordon, Lady. (Lucille Christiana Sutherland) ("Mrs Morgan")',
       'Robbins, Mr. Victor', 'Taussig, Mrs. Emil (Tillie Mandelbaum)',
       'de Messemaeker, Mrs. Guillaume Joseph (Emma)',
       'Morrow, Mr. Thomas Rowan', 'Sivic, Mr. Husein',
       'Norman, Mr. Robert Douglas', 'Simmons, Mr. John',
       'Meanwell, Miss. (Marion Ogden)', 'Davies, Mr. Alfred J',
       'Stoytcheff, Mr. Ilia',
       'Palsson, Mrs. Nils (Alma Cornelia Berglund)',
       'Doharr, Mr. Tannous', 'Jonsson, Mr. Carl', 'Harris, Mr. George',
       'Appleton, Mrs. Edward Dale (Charlotte Lamson)',
       'Flynn, Mr. John Irwin ("Irving")', 'Kelly, Miss. Mary',
       'Rush, Mr. Alfred George John', 'Patchett, Mr. George',
       'Garside, Miss. Ethel',
       'Silvey, Mrs. William Baird (Alice Munger)',
       'Caram, Mrs. Joseph (Maria Elias)', 'Jussila, Mr. Eiriik',
       'Christy, Miss. Julie Rachel',
       'Thayer, Mrs. John Borland (Marian Longstreth Morris)',
       'Downton, Mr. William James', 'Ross, Mr. John Hugo',
       'Paulner, Mr. Uscher', 'Taussig, Miss. Ruth',
       'Jarvis, Mr. John Denzil', 'Frolicher-Stehli, Mr. Maxmillian',
       'Gilinski, Mr. Eliezer', 'Murdlin, Mr. Joseph',
       'Rintamaki, Mr. Matti',
       'Stephenson, Mrs. Walter Bertram (Martha Eustis)',
       'Elsbury, Mr. William James', 'Bourke, Miss. Mary',
       'Chapman, Mr. John Henry', 'Van Impe, Mr. Jean Baptiste',
       'Leitch, Miss. Jessie Wills', 'Johnson, Mr. Alfred',
       'Boulos, Mr. Hanna',
       'Duff Gordon, Sir. Cosmo Edmund ("Mr Morgan")',
       'Jacobsohn, Mrs. Sidney Samuel (Amy Frances Christy)',
       'Slabenoff, Mr. Petco', 'Harrington, Mr. Charles H',
       'Torber, Mr. Ernst William', 'Homer, Mr. Harry ("Mr E Haven")',
       'Lindell, Mr. Edvard Bengtsson', 'Karaic, Mr. Milan',
       'Daniel, Mr. Robert Williams',
       'Laroche, Mrs. Joseph (Juliette Marie Louise Lafargue)',
       'Shutes, Miss. Elizabeth W',
       'Andersson, Mrs. Anders Johan (Alfrida Konstantia Brogren)',
       'Jardin, Mr. Jose Neto', 'Murphy, Miss. Margaret Jane',
       'Horgan, Mr. John', 'Brocklebank, Mr. William Alfred',
       'Herman, Miss. Alice', 'Danbom, Mr. Ernst Gilbert',
       'Lobb, Mrs. William Arthur (Cordelia K Stanlick)',
       'Becker, Miss. Marion Louise', 'Gavey, Mr. Lawrence',
       'Yasbeck, Mr. Antoni', 'Kimball, Mr. Edwin Nelson Jr',
       'Nakid, Mr. Sahid', 'Hansen, Mr. Henry Damsgaard',
       'Bowen, Mr. David John "Dai"', 'Sutton, Mr. Frederick',
       'Kirkland, Rev. Charles Leonard', 'Longley, Miss. Gretchen Fiske',
       'Bostandyeff, Mr. Guentcho', "O'Connell, Mr. Patrick D",
       'Barkworth, Mr. Algernon Henry Wilson',
       'Lundahl, Mr. Johan Svensson', 'Stahelin-Maeglin, Dr. Max',
       'Parr, Mr. William Henry Marsh', 'Skoog, Miss. Mabel',
       'Davis, Miss. Mary', 'Leinonen, Mr. Antti Gustaf',
       'Collyer, Mr. Harvey', 'Panula, Mrs. Juha (Maria Emilia Ojala)',
       'Thorneycroft, Mr. Percival', 'Jensen, Mr. Hans Peder',
       'Sagesser, Mlle. Emma', 'Skoog, Miss. Margit Elizabeth',
       'Foo, Mr. Choong', 'Baclini, Miss. Eugenie',
       'Harper, Mr. Henry Sleeper', 'Cor, Mr. Liudevit',
       'Simonius-Blumer, Col. Oberst Alfons', 'Willey, Mr. Edward',
       'Stanley, Miss. Amy Zillah Elsie', 'Mitkoff, Mr. Mito',
       'Doling, Miss. Elsie', 'Kalvik, Mr. Johannes Halvorsen',
       'O\'Leary, Miss. Hanora "Norah"', 'Hegarty, Miss. Hanora "Nora"',
       'Hickman, Mr. Leonard Mark', 'Radeff, Mr. Alexander',
       'Bourke, Mrs. John (Catherine)', 'Eitemiller, Mr. George Floyd',
       'Newell, Mr. Arthur Webster', 'Frauenthal, Dr. Henry William',
       'Badt, Mr. Mohamed', 'Colley, Mr. Edward Pomeroy',
       'Coleff, Mr. Peju', 'Lindqvist, Mr. Eino William',
       'Hickman, Mr. Lewis', 'Butler, Mr. Reginald Fenton',
       'Rommetvedt, Mr. Knud Paust', 'Cook, Mr. Jacob',
       'Taylor, Mrs. Elmer Zebley (Juliet Cummins Wright)',
       'Brown, Mrs. Thomas William Solomon (Elizabeth Catherine Ford)',
       'Davidson, Mr. Thornton', 'Mitchell, Mr. Henry Michael',
       'Wilhelms, Mr. Charles', 'Watson, Mr. Ennis Hastings',
       'Edvardsson, Mr. Gustaf Hjalmar', 'Sawyer, Mr. Frederick Charles',
       'Turja, Miss. Anna Sofia',
       'Goodwin, Mrs. Frederick (Augusta Tyler)',
       'Cardeza, Mr. Thomas Drake Martinez', 'Peters, Miss. Katie',
       'Hassab, Mr. Hammad', 'Olsvigen, Mr. Thor Anderson',
       'Goodwin, Mr. Charles Edward', 'Brown, Mr. Thomas William Solomon',
       'Laroche, Mr. Joseph Philippe Lemercier',
       'Panula, Mr. Jaako Arnold', 'Dakic, Mr. Branko',
       'Fischer, Mr. Eberhard Thelander',
       'Madill, Miss. Georgette Alexandra', 'Dick, Mr. Albert Adrian',
       'Karun, Miss. Manca', 'Lam, Mr. Ali', 'Saad, Mr. Khalil',
       'Weir, Col. John', 'Chapman, Mr. Charles Henry',
       'Kelly, Mr. James', 'Mullens, Miss. Katherine "Katie"',
       'Thayer, Mr. John Borland',
       'Humblen, Mr. Adolf Mathias Nicolai Olsen',
       'Astor, Mrs. John Jacob (Madeleine Talmadge Force)',
       'Silverthorne, Mr. Spencer Victor', 'Barbara, Miss. Saiide',
       'Gallagher, Mr. Martin', 'Hansen, Mr. Henrik Juul',
       'Morley, Mr. Henry Samuel ("Mr Henry Marshall")',
       'Kelly, Mrs. Florence "Fannie"',
       'Calderhead, Mr. Edward Pennington', 'Cleaver, Miss. Alice',
       'Moubarek, Master. Halim Gonios ("William George")',
       'Mayne, Mlle. Berthe Antonine ("Mrs de Villiers")',
       'Klaber, Mr. Herman', 'Taylor, Mr. Elmer Zebley',
       'Larsson, Mr. August Viktor', 'Greenberg, Mr. Samuel',
       'Soholt, Mr. Peter Andreas Lauritz Andersen',
       'Endres, Miss. Caroline Louise',
       'Troutt, Miss. Edwina Celia "Winnie"', 'McEvoy, Mr. Michael',
       'Johnson, Mr. Malkolm Joackim',
       'Harper, Miss. Annie Jessie "Nina"', 'Jensen, Mr. Svend Lauritz',
       'Gillespie, Mr. William Henry', 'Hodges, Mr. Henry Price',
       'Chambers, Mr. Norman Campbell', 'Oreskovic, Mr. Luka',
       'Renouf, Mrs. Peter Henry (Lillian Jefferys)',
       'Mannion, Miss. Margareth', 'Bryhl, Mr. Kurt Arnold Gottfrid',
       'Ilmakangas, Miss. Pieta Sofia', 'Allen, Miss. Elisabeth Walton',
       'Hassan, Mr. Houssein G N', 'Knight, Mr. Robert J',
       'Berriman, Mr. William John', 'Troupiansky, Mr. Moses Aaron',
       'Williams, Mr. Leslie', 'Ford, Mrs. Edward (Margaret Ann Watson)',
       'Lesurer, Mr. Gustave J', 'Ivanoff, Mr. Kanio',
       'Nankoff, Mr. Minko', 'Hawksford, Mr. Walter James',
       'Cavendish, Mr. Tyrell William',
       'Ryerson, Miss. Susan Parker "Suzette"', 'McNamee, Mr. Neal',
       'Stranden, Mr. Juho', 'Crosby, Capt. Edward Gifford',
       'Abbott, Mr. Rossmore Edward', 'Sinkkonen, Miss. Anna',
       'Marvin, Mr. Daniel Warner', 'Connaghton, Mr. Michael',
       'Wells, Miss. Joan', 'Moor, Master. Meier',
       'Vande Velde, Mr. Johannes Joseph', 'Jonkoff, Mr. Lalio',
       'Herman, Mrs. Samuel (Jane Laver)', 'Hamalainen, Master. Viljo',
       'Carlsson, Mr. August Sigfrid', 'Bailey, Mr. Percy Andrew',
       'Theobald, Mr. Thomas Leonard',
       'Rothes, the Countess. of (Lucy Noel Martha Dyer-Edwards)',
       'Garfirth, Mr. John', 'Nirva, Mr. Iisakki Antino Aijo',
       'Barah, Mr. Hanna Assi',
       'Carter, Mrs. William Ernest (Lucile Polk)',
       'Eklund, Mr. Hans Linus', 'Hogeboom, Mrs. John C (Anna Andrews)',
       'Brewe, Dr. Arthur Jackson', 'Mangan, Miss. Mary',
       'Moran, Mr. Daniel J', 'Gronnestad, Mr. Daniel Danielsen',
       'Lievens, Mr. Rene Aime', 'Jensen, Mr. Niels Peder',
       'Mack, Mrs. (Mary)', 'Elias, Mr. Dibo',
       'Hocking, Mrs. Elizabeth (Eliza Needs)',
       'Myhrman, Mr. Pehr Fabian Oliver Malkolm', 'Tobin, Mr. Roger',
       'Emanuel, Miss. Virginia Ethel', 'Kilgannon, Mr. Thomas J',
       'Robert, Mrs. Edward Scott (Elisabeth Walton McMillan)',
       'Ayoub, Miss. Banoura',
       'Dick, Mrs. Albert Adrian (Vera Gillespie)',
       'Long, Mr. Milton Clyde', 'Johnston, Mr. Andrew G',
       'Ali, Mr. William', 'Harmer, Mr. Abraham (David Lishin)',
       'Sjoblom, Miss. Anna Sofia', 'Rice, Master. George Hugh',
       'Dean, Master. Bertram Vere', 'Guggenheim, Mr. Benjamin',
       'Keane, Mr. Andrew "Andy"', 'Gaskell, Mr. Alfred',
       'Sage, Miss. Stella Anna', 'Hoyt, Mr. William Fisher',
       'Dantcheff, Mr. Ristiu', 'Otter, Mr. Richard',
       'Leader, Dr. Alice (Farnham)', 'Osman, Mrs. Mara',
       'Ibrahim Shawah, Mr. Yousseff',
       'Van Impe, Mrs. Jean Baptiste (Rosalie Paula Govaert)',
       'Ponesell, Mr. Martin',
       'Collyer, Mrs. Harvey (Charlotte Annie Tate)',
       'Carter, Master. William Thornton II',
       'Thomas, Master. Assad Alexander', 'Hedman, Mr. Oskar Arvid',
       'Johansson, Mr. Karl Johan', 'Andrews, Mr. Thomas Jr',
       'Pettersson, Miss. Ellen Natalia', 'Meyer, Mr. August',
       'Chambers, Mrs. Norman Campbell (Bertha Griggs)',
       'Alexander, Mr. William', 'Lester, Mr. James',
       'Slemen, Mr. Richard James', 'Andersson, Miss. Ebba Iris Alfrida',
       'Tomlin, Mr. Ernest Portage', 'Fry, Mr. Richard',
       'Heininen, Miss. Wendla Maria', 'Mallet, Mr. Albert',
       'Holm, Mr. John Fredrik Alexander', 'Skoog, Master. Karl Thorsten',
       'Hays, Mrs. Charles Melville (Clara Jennings Gregg)',
       'Lulic, Mr. Nikola', 'Reuchlin, Jonkheer. John George',
       'Moor, Mrs. (Beila)', 'Panula, Master. Urho Abraham',
       'Flynn, Mr. John', 'Lam, Mr. Len', 'Mallet, Master. Andre',
       'McCormack, Mr. Thomas Joseph',
       'Stone, Mrs. George Nelson (Martha Evelyn)',
       'Yasbeck, Mrs. Antoni (Selini Alexander)',
       'Richards, Master. George Sibley', 'Saad, Mr. Amin',
       'Augustsson, Mr. Albert', 'Allum, Mr. Owen George',
       'Compton, Miss. Sara Rebecca', 'Pasic, Mr. Jakob',
       'Sirota, Mr. Maurice', 'Chip, Mr. Chang', 'Marechal, Mr. Pierre',
       'Alhomaki, Mr. Ilmari Rudolf', 'Mudd, Mr. Thomas Charles',
       'Serepeca, Miss. Augusta', 'Lemberopolous, Mr. Peter L',
       'Culumovic, Mr. Jeso', 'Abbing, Mr. Anthony',
       'Sage, Mr. Douglas Bullen', 'Markoff, Mr. Marin',
       'Harper, Rev. John',
       'Goldenberg, Mrs. Samuel L (Edwiga Grabowska)',
       'Andersson, Master. Sigvard Harald Elias', 'Svensson, Mr. Johan',
       'Boulos, Miss. Nourelain', 'Lines, Miss. Mary Conover',
       'Carter, Mrs. Ernest Courtenay (Lilian Hughes)',
       'Aks, Mrs. Sam (Leah Rosen)',
       'Wick, Mrs. George Dennick (Mary Hitchcock)',
       'Daly, Mr. Peter Denis ', 'Baclini, Mrs. Solomon (Latifa Qurban)',
       'Razi, Mr. Raihed', 'Hansen, Mr. Claus Peter',
       'Giles, Mr. Frederick Edward',
       'Swift, Mrs. Frederick Joel (Margaret Welles Barron)',
       'Sage, Miss. Dorothy Edith "Dolly"', 'Gill, Mr. John William',
       'Bystrom, Mrs. (Karolina)', 'Duran y More, Miss. Asuncion',
       'Roebling, Mr. Washington Augustus II',
       'van Melkebeke, Mr. Philemon', 'Johnson, Master. Harold Theodor',
       'Balkic, Mr. Cerin',
       'Beckwith, Mrs. Richard Leonard (Sallie Monypeny)',
       'Carlsson, Mr. Frans Olof', 'Vander Cruyssen, Mr. Victor',
       'Abelson, Mrs. Samuel (Hannah Wizosky)',
       'Najib, Miss. Adele Kiamie "Jane"',
       'Gustafsson, Mr. Alfred Ossian', 'Petroff, Mr. Nedelio',
       'Laleff, Mr. Kristo',
       'Potter, Mrs. Thomas Jr (Lily Alexenia Wilson)',
       'Shelley, Mrs. William (Imanita Parrish Hall)',
       'Markun, Mr. Johann', 'Dahlberg, Miss. Gerda Ulrika',
       'Banfield, Mr. Frederick James', 'Sutehall, Mr. Henry Jr',
       'Rice, Mrs. William (Margaret Norton)', 'Montvila, Rev. Juozas',
       'Graham, Miss. Margaret Edith',
       'Johnston, Miss. Catherine Helen "Carrie"',
       'Behr, Mr. Karl Howell', 'Dooley, Mr. Patrick'], dtype=object)


df['Embarked'].unique()

array(['S', 'C', 'Q', nan], dtype=object)


df['Survived'].unique()

array([0, 1])


df['Pclass']

PassengerId
1      3
2      1
3      3
4      1
5      3
6      3
7      1
8      3
9      3
10     2
11     3
12     1
13     3
14     3
15     3
16     2
17     3
18     2
19     3
20     3
21     2
22     2
23     3
24     1
25     3
26     3
27     3
28     1
29     3
30     3
      ..
862    2
863    1
864    3
865    2
866    2
867    2
868    1
869    3
870    3
871    3
872    1
873    1
874    3
875    2
876    3
877    3
878    3
879    3
880    1
881    2
882    3
883    3
884    2
885    3
886    3
887    2
888    1
889    3
890    1
891    3
Name: Pclass, Length: 891, dtype: int64


df['Pclass'].unique()

array([3, 1, 2])


import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns


atheletes_df = pd.read_csv('athlete_events.csv')
regions_df = pd.read_csv('noc_regions.csv')


data_df = pd.merge(atheletes_df, regions_df, on='NOC', how='left')


data_df.head()


data_df.columns

Index(['ID', 'Name', 'Sex', 'Age', 'Height', 'Weight', 'Team', 'NOC', 'Games',
       'Year', 'Season', 'City', 'Sport', 'Event', 'Medal', 'region', 'notes'],
      dtype='object')


data_df.describe()


data_df.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 271116 entries, 0 to 271115
Data columns (total 17 columns):
ID        271116 non-null int64
Name      271116 non-null object
Sex       271116 non-null object
Age       261642 non-null float64
Height    210945 non-null float64
Weight    208241 non-null float64
Team      271116 non-null object
NOC       271116 non-null object
Games     271116 non-null object
Year      271116 non-null int64
Season    271116 non-null object
City      271116 non-null object
Sport     271116 non-null object
Event     271116 non-null object
Medal     39783 non-null object
region    270746 non-null object
notes     5039 non-null object
dtypes: float64(3), int64(2), object(12)
memory usage: 37.2+ MB


sns.distplot(data_df['Age'])

/home/kashif/anaconda3/lib/python3.7/site-packages/scipy/stats/stats.py:1713: FutureWarning: Using a non-tuple sequence for multidimensional indexing is deprecated; use `arr[tuple(seq)]` instead of `arr[seq]`. In the future this will be interpreted as an array index, `arr[np.array(seq)]`, which will result either in an error or a different result.
  return np.add.reduce(sorted[indexer] * weights, axis=axis) / sumval
/home/kashif/anaconda3/lib/python3.7/site-packages/numpy/core/_methods.py:28: RuntimeWarning: invalid value encountered in reduce
  return umr_maximum(a, axis, None, out, keepdims, initial)
/home/kashif/anaconda3/lib/python3.7/site-packages/numpy/core/_methods.py:32: RuntimeWarning: invalid value encountered in reduce
  return umr_minimum(a, axis, None, out, keepdims, initial)

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-8-8331d431a2ca> in <module>
----> 1 sns.distplot(data_df['Age'])

~/anaconda3/lib/python3.7/site-packages/seaborn/distributions.py in distplot(a, bins, hist, kde, rug, fit, hist_kws, kde_kws, rug_kws, fit_kws, color, vertical, norm_hist, axlabel, label, ax)
    213     if hist:
    214         if bins is None:
--> 215             bins = min(_freedman_diaconis_bins(a), 50)
    216         hist_kws.setdefault("alpha", 0.4)
    217         if LooseVersion(mpl.__version__) < LooseVersion("2.2"):

~/anaconda3/lib/python3.7/site-packages/seaborn/distributions.py in _freedman_diaconis_bins(a)
     37         return int(np.sqrt(a.size))
     38     else:
---> 39         return int(np.ceil((a.max() - a.min()) / h))
     40 
     41 

ValueError: cannot convert float NaN to integer


age_df = data_df['Age']


age_df = pd.to_numeric(data_df['Age'], errors='coerce')
age_df = age_df.dropna()
age_df = age_df.astype(int)


age_df

0         24
1         23
2         24
3         34
4         21
5         21
6         25
7         25
8         27
9         27
10        31
11        31
12        31
13        31
14        33
15        33
16        33
17        33
18        31
19        31
20        31
21        31
22        33
23        33
24        33
25        33
26        18
27        18
28        26
29        26
          ..
271086    23
271087    19
271088    19
271089    34
271090    38
271091    32
271092    21
271093    21
271094    25
271095    25
271096    29
271097    29
271098    33
271099    36
271100    26
271101    24
271102    19
271103    23
271104    22
271105    23
271106    27
271107    21
271108    24
271109    28
271110    33
271111    29
271112    27
271113    27
271114    30
271115    34
Name: Age, Length: 261642, dtype: int64


sns.countplot(age_df)

<matplotlib.axes._subplots.AxesSubplot at 0x7f28ef021470>


data_df.loc[data_df['Medal'].isnull()]


medalists_df = data_df.loc[~data_df['Medal'].isnull()]


medalists_df


def plot_column(my_df, col, chart_type='Histogram', dtype=int,
               bin_size=25):
    temp_df = pd.to_numeric(my_df[col], errors='coerce')
    temp_df = temp_df.dropna()
    temp_df = temp_df.astype(dtype)
    if chart_type=='Histogram':
        ax = sns.countplot(temp_df)
    elif chart_type=='Density':
        ax = sns.distplot(temp_df)
    xmin, xmax = ax.get_xlim()
    ax.set_xticks(np.round(np.linspace(xmin, xmax, bin_size), 2))
    plt.tight_layout()
    plt.locator_params(axis='y', nbins=6)
    plt.show()


plot_column(medalists_df, 'Age')


from scipy.stats import skew
age_df = pd.to_numeric(medalists_df['Age'], errors='coerce')
age_df = age_df.dropna()
age_df = age_df.astype(int)
print("Skewness is {}".format(skew(age_df)))
print("Mean is {}".format(np.mean(age_df)))
print("Median is {}".format(np.median(age_df)))

Skewness is 1.497531959387686
Mean is 25.925174771452717
Median is 25.0


plot_column(medalists_df, 'Height', bin_size=15)


Height_df = pd.to_numeric(medalists_df['Height'], errors='coerce')
Height_df = Height_df.dropna()
Height_df = Height_df.astype(int)
print("Skewness is {}".format(skew(Height_df)))
print("Mean is {}".format(np.mean(Height_df)))
print("Median is {}".format(np.median(Height_df)))

Skewness is 0.046825246979302765
Mean is 177.55419670442842
Median is 178.0


plot_column(medalists_df, 'Weight', bin_size=15)


Weight_df = pd.to_numeric(medalists_df['Weight'], errors='coerce')
Weight_df = Weight_df.dropna()
Weight_df = Weight_df.astype(int)
print("Skewness is {}".format(skew(Weight_df)))
print("Mean is {}".format(np.mean(Weight_df)))
print("Median is {}".format(np.median(Weight_df)))

Skewness is 0.6921002780813605
Mean is 73.76723798266352
Median is 73.0


sports_df = medalists_df[~medalists_df['Sport'].isnull()]
sns.countplot(medalists_df['Sport'])

<matplotlib.axes._subplots.AxesSubplot at 0x7f28e62802b0>


sum(medalists_df['Sport'].isnull())


sports_count=medalists_df['Sport'].value_counts().nlargest(25).to_frame()


#sports_count.reset_index(inplace=True)
print(sports_count)

                      Sport
Athletics              3969
Swimming               3048
Rowing                 2945
Gymnastics             2256
Fencing                1743
Football               1571
Ice Hockey             1530
Hockey                 1528
Wrestling              1296
Cycling                1263
Sailing                1232
Shooting               1228
Canoeing               1165
Basketball             1080
Handball               1060
Water Polo             1057
Volleyball              969
Equestrianism           965
Boxing                  944
Cross Country Skiing    776
Weightlifting           646
Speed Skating           580
Judo                    547
Alpine Skiing           428
Diving                  427


ax = sports_count.plot.bar(y='Sport')
ax.get_legend().remove()


year_count_df=data_df['Year'].value_counts().to_frame()


year_count_df.sort_index(inplace=True)
ax = year_count_df.plot.bar(y='Year')
ax.get_legend().remove()


import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
%matplotlib inline


titanic_data_df = pd.read_csv('titanic-data.csv')


g = sns.countplot(x='Sex', hue='Survived', data=titanic_data_df)


g = sns.catplot(x="Embarked", col="Survived",
                 data=titanic_data_df, kind="count",
                 height=4, aspect=.7);


g = sns.countplot(x='Embarked', hue='Survived', data=titanic_data_df)


g = sns.countplot(x='Embarked', hue='Pclass', data=titanic_data_df)


g = sns.countplot(x='Pclass', hue='Survived', data=titanic_data_df)


#Function to add new column 'FamilySize'
def add_family(df):
    df['FamilySize'] = df['SibSp'] + df['Parch'] + 1 
    return df

titanic_data_df = add_family(titanic_data_df)
titanic_data_df.head(10)


g = sns.countplot(x="FamilySize", hue="Survived",
                 data=titanic_data_df);


g = sns.countplot(x="FamilySize", hue="Sex",
                 data=titanic_data_df);


age_df = titanic_data_df[~titanic_data_df['Age'].isnull()]
#Make bins and group all passengers into these bins and store those values in a new column 'ageGroup'
age_bins = ['0-9', '10-19', '20-29', '30-39', '40-49', '50-59', '60-69', '70-79']
age_df['ageGroup'] = pd.cut(titanic_data_df.Age, range(0, 81, 10), right=False, labels=age_bins)

/home/kashif/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:4: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy
  after removing the cwd from sys.path.


#age_df[['Age', 'ageGroup']]


sns.countplot(x='ageGroup', hue='Survived', data=age_df)

<matplotlib.axes._subplots.AxesSubplot at 0x7fd1996c6940>


import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
%matplotlib inline


pokemon_df = pd.read_csv('Pokemon.csv', index_col=0)


pokemon_df.head()


pokemon_df.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 800 entries, 1 to 721
Data columns (total 12 columns):
Name          800 non-null object
Type 1        800 non-null object
Type 2        414 non-null object
Total         800 non-null int64
HP            800 non-null int64
Attack        800 non-null int64
Defense       800 non-null int64
Sp. Atk       800 non-null int64
Sp. Def       800 non-null int64
Speed         800 non-null int64
Generation    800 non-null int64
Legendary     800 non-null bool
dtypes: bool(1), int64(8), object(3)
memory usage: 75.8+ KB


pokemon_df.describe()


pokemon_df['Type 2'].fillna(value='NA', inplace=True)


pokemon_df.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 800 entries, 1 to 721
Data columns (total 12 columns):
Name          800 non-null object
Type 1        800 non-null object
Type 2        800 non-null object
Total         800 non-null int64
HP            800 non-null int64
Attack        800 non-null int64
Defense       800 non-null int64
Sp. Atk       800 non-null int64
Sp. Def       800 non-null int64
Speed         800 non-null int64
Generation    800 non-null int64
Legendary     800 non-null bool
dtypes: bool(1), int64(8), object(3)
memory usage: 75.8+ KB


legendry_df = pokemon_df[pokemon_df['Legendary']==True]


ax = sns.countplot(pokemon_df['Type 1'])
g= ax.set_xticklabels(ax.get_xticklabels(), rotation=90)


ax = sns.countplot(pokemon_df[pokemon_df['Type 2']!='NA']['Type 2'])
g= ax.set_xticklabels(ax.get_xticklabels(), rotation=90)


pokemon_df.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 800 entries, 1 to 721
Data columns (total 12 columns):
Name          800 non-null object
Type 1        800 non-null object
Type 2        800 non-null object
Total         800 non-null int64
HP            800 non-null int64
Attack        800 non-null int64
Defense       800 non-null int64
Sp. Atk       800 non-null int64
Sp. Def       800 non-null int64
Speed         800 non-null int64
Generation    800 non-null int64
Legendary     800 non-null bool
dtypes: bool(1), int64(8), object(3)
memory usage: 95.8+ KB


plt.subplots(figsize = (20,5))
plt.title('Attack by Type1')
sns.boxplot(x = "Type 1", y = "Attack",data = pokemon_df)

<matplotlib.axes._subplots.AxesSubplot at 0x7f0e80ea1240>


plt.subplots(figsize = (20,5))
plt.title('Attack by Type2')
sns.boxplot(x = "Type 2", y = "Attack",data = pokemon_df)

<matplotlib.axes._subplots.AxesSubplot at 0x7f0e8098b208>


plt.subplots(figsize = (20,5))
plt.title('Defense by Type1')
sns.boxplot(x = "Type 1", y = "Defense",data = pokemon_df)

<matplotlib.axes._subplots.AxesSubplot at 0x7f0e88968198>


plt.subplots(figsize = (20,5))
plt.title('Defense by Type2')
sns.boxplot(x = "Type 2", y = "Defense",data = pokemon_df)

<matplotlib.axes._subplots.AxesSubplot at 0x7f0e819622e8>


type_grouped = pokemon_df[pokemon_df['Type 2']!='NA'].groupby(['Type 1', 'Type 2']).size()
print(type_grouped)

Type 1    Type 2  
Bug       Electric     2
          Fighting     2
          Fire         2
          Flying      14
          Ghost        1
          Grass        6
          Ground       2
          Poison      12
          Rock         3
          Steel        7
          Water        1
Dark      Dragon       3
          Fighting     2
          Fire         3
          Flying       5
          Ghost        2
          Ice          2
          Psychic      2
          Steel        2
Dragon    Electric     1
          Fairy        1
          Fire         1
          Flying       6
          Ground       5
          Ice          3
          Psychic      4
Electric  Dragon       1
          Fairy        1
          Fire         1
          Flying       5
                      ..
Rock      Fighting     1
          Flying       4
          Grass        2
          Ground       6
          Ice          2
          Psychic      2
          Steel        3
          Water        6
Steel     Dragon       1
          Fairy        3
          Fighting     1
          Flying       1
          Ghost        4
          Ground       2
          Psychic      7
          Rock         3
Water     Dark         6
          Dragon       2
          Electric     2
          Fairy        2
          Fighting     3
          Flying       7
          Ghost        2
          Grass        3
          Ground      10
          Ice          3
          Poison       3
          Psychic      5
          Rock         4
          Steel        1
Length: 136, dtype: int64


sns.set(rc={'figure.figsize':(11,8)})
sns.heatmap(
    type_grouped.unstack(),
    annot=True,
)
plt.xticks(rotation=90)
plt.show()


type_grouped = legendry_df[legendry_df['Type 2']!='NA'].groupby(['Type 1', 'Type 2']).size()
sns.set(rc={'figure.figsize':(11,8)})
sns.heatmap(
    type_grouped.unstack(),
    annot=True,
)
plt.xticks(rotation=90)
plt.show()


pokemon_gen = legendry_df.groupby('Generation')['Name'].count()
sns.lineplot(data=pokemon_gen)

<matplotlib.axes._subplots.AxesSubplot at 0x7f0e7bed1ac8>


legendry_df[legendry_df['Generation']==3]


legendry_df[legendry_df['Generation']==5]


max_type1_per_gen = pokemon_df.groupby(['Generation','Type 1']).size()


max_type1_per_gen.unstack().plot()

<matplotlib.axes._subplots.AxesSubplot at 0x7f0e8426f5c0>


# type1_per_gen = pd.DataFrame({'count' : pokemon_df.groupby( [ "Generation", "Type 1"] ).size()}).reset_index()
# print(pokemon_df.groupby( [ "Generation", "Type 1"] ).size())


from bokeh.palettes import Spectral11
from bokeh.plotting import figure, output_file, show
from bokeh.models import Legend, LegendItem
p = figure(plot_width=800, plot_height=550, x_range=(1, 7))
p.background_fill_color = "beige"

p.title.text = 'Click on legend entries to hide the corresponding lines'
import random
legend_list = []
for type_id in type1_per_gen['Type 1'].unique():
    color = random.choice(Spectral11)
    df = pd.DataFrame(type1_per_gen[type1_per_gen['Type 1']==type_id])
    p.line(df['Generation'], df['count'], line_width=2, alpha=0.8, color=color, legend=type_id)

p.legend.location = "top_right"
p.legend.click_policy="hide"

show(p)


pokemon_df.groupby([ "Generation", "Type 1"])[['Total']].max()


# type1_total_gen = pd.DataFrame({'Total' : pokemon_df.groupby( [ "Generation", "Type 1"] )['Total'].max()}).reset_index()
# print(pokemon_df.groupby( [ "Generation", "Type 1"] )['Total'].max())


from bokeh.palettes import Spectral11
from bokeh.plotting import figure, output_file, show
from bokeh.models import Legend, LegendItem
p = figure(plot_width=800, plot_height=550, x_range=(1, 7))
p.background_fill_color = "beige"

p.title.text = 'Click on legend entries to hide the corresponding lines'
import random
legend_list = []
for type_id in type1_total_gen['Type 1'].unique():
    color = random.choice(Spectral11)
    df = pd.DataFrame(type1_total_gen[type1_total_gen['Type 1']==type_id])
    p.line(df['Generation'], df['Total'], line_width=2, alpha=0.8, color=color, legend=type_id)

p.legend.location = "top_right"
p.legend.click_policy="hide"

show(p)


import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
%matplotlib inline


red_wine_df = pd.read_csv('winequality-red.csv', delimiter=';')


red_wine_df.head()


red_wine_df.columns

Index(['fixed acidity', 'volatile acidity', 'citric acid', 'residual sugar',
       'chlorides', 'free sulfur dioxide', 'total sulfur dioxide', 'density',
       'pH', 'sulphates', 'alcohol', 'quality'],
      dtype='object')


red_wine_df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1599 entries, 0 to 1598
Data columns (total 12 columns):
fixed acidity           1599 non-null float64
volatile acidity        1599 non-null float64
citric acid             1599 non-null float64
residual sugar          1599 non-null float64
chlorides               1599 non-null float64
free sulfur dioxide     1599 non-null float64
total sulfur dioxide    1599 non-null float64
density                 1599 non-null float64
pH                      1599 non-null float64
sulphates               1599 non-null float64
alcohol                 1599 non-null float64
quality                 1599 non-null int64
dtypes: float64(11), int64(1)
memory usage: 150.0 KB


red_wine_df.describe()


red_wine_df['quality']

0       5
1       5
2       5
3       6
4       5
5       5
6       5
7       7
8       7
9       5
10      5
11      5
12      5
13      5
14      5
15      5
16      7
17      5
18      4
19      6
20      6
21      5
22      5
23      5
24      6
25      5
26      5
27      5
28      5
29      6
       ..
1569    6
1570    6
1571    6
1572    5
1573    6
1574    6
1575    6
1576    6
1577    6
1578    6
1579    5
1580    6
1581    5
1582    5
1583    5
1584    7
1585    6
1586    6
1587    6
1588    6
1589    5
1590    6
1591    6
1592    6
1593    6
1594    5
1595    6
1596    6
1597    5
1598    6
Name: quality, Length: 1599, dtype: int64


red_wine_df.describe()


sns.set(rc={'figure.figsize':(7,6)})
sns.countplot(red_wine_df['quality'])

<matplotlib.axes._subplots.AxesSubplot at 0x7fdf97f15eb8>


sns.pairplot(red_wine_df)

<seaborn.axisgrid.PairGrid at 0x7fdf97f29be0>


sns.set(rc={'figure.figsize':(12,10)})
sns.heatmap(red_wine_df.corr(), annot=True, fmt='.2f', linewidths=2)

<matplotlib.axes._subplots.AxesSubplot at 0x7fdf94860390>


sns.distplot(red_wine_df['alcohol'])

/home/kashif/anaconda3/lib/python3.7/site-packages/scipy/stats/stats.py:1713: FutureWarning: Using a non-tuple sequence for multidimensional indexing is deprecated; use `arr[tuple(seq)]` instead of `arr[seq]`. In the future this will be interpreted as an array index, `arr[np.array(seq)]`, which will result either in an error or a different result.
  return np.add.reduce(sorted[indexer] * weights, axis=axis) / sumval

<matplotlib.axes._subplots.AxesSubplot at 0x7fdf88fbc588>


from scipy.stats import skew
skew(red_wine_df['alcohol'])

0.8600210646566755


def draw_hist(temp_df, bin_size = 15):
    ax = sns.distplot(temp_df)
    #xmin, xmax = ax.get_xlim()
    #ax.set_xticks(np.round(np.linspace(xmin, xmax, bin_size), 2))
    plt.tight_layout()
    plt.locator_params(axis='y', nbins=6)
    plt.show()
    print("Skewness is {}".format(skew(temp_df)))
    print("Mean is {}".format(np.median(temp_df)))
    print("Median is {}".format(np.mean(temp_df)))


draw_hist(red_wine_df['alcohol'])

/home/kashif/anaconda3/lib/python3.7/site-packages/scipy/stats/stats.py:1713: FutureWarning: Using a non-tuple sequence for multidimensional indexing is deprecated; use `arr[tuple(seq)]` instead of `arr[seq]`. In the future this will be interpreted as an array index, `arr[np.array(seq)]`, which will result either in an error or a different result.
  return np.add.reduce(sorted[indexer] * weights, axis=axis) / sumval

Skewness is 0.8600210646566755
Mean is 10.2
Median is 10.422983114446502


sns.boxplot(x='quality', y='alcohol', data=red_wine_df)

<matplotlib.axes._subplots.AxesSubplot at 0x7fdf88a28518>


sns.boxplot(x='quality', y='alcohol', data=red_wine_df,
           showfliers=False)

<matplotlib.axes._subplots.AxesSubplot at 0x7fdf87abf5f8>


joint_plt = sns.jointplot(x='alcohol', y='pH', data=red_wine_df,
                        kind='reg')

/home/kashif/anaconda3/lib/python3.7/site-packages/scipy/stats/stats.py:1713: FutureWarning: Using a non-tuple sequence for multidimensional indexing is deprecated; use `arr[tuple(seq)]` instead of `arr[seq]`. In the future this will be interpreted as an array index, `arr[np.array(seq)]`, which will result either in an error or a different result.
  return np.add.reduce(sorted[indexer] * weights, axis=axis) / sumval


from scipy.stats import pearsonr
def get_corr(col1, col2, temp_df):
    pearson_corr, p_value = pearsonr(temp_df[col1], temp_df[col2])
    print("Correlation between {} and {} is {}".format(col1, col2, pearson_corr))
    print("P-value of this correlation is {}".format(p_value))


get_corr('alcohol', 'pH', red_wine_df)

Correlation between alcohol and pH is 0.20563250850549822
P-value of this correlation is 9.964497741460977e-17


joint_plt = sns.jointplot(x='alcohol', y='density', data=red_wine_df,
                        kind='reg')


get_corr('alcohol', 'density', red_wine_df)

Correlation between alcohol and density is -0.4961797702417011
P-value of this correlation is 3.938835339991827e-100


g = sns.FacetGrid(red_wine_df, col="quality")
g = g.map(sns.regplot, "density", "alcohol")


sns.boxplot(x='quality', y='sulphates', data=red_wine_df)

<matplotlib.axes._subplots.AxesSubplot at 0x7fdf861a4f60>


sns.boxplot(x='quality', y='total sulfur dioxide', data=red_wine_df)

<matplotlib.axes._subplots.AxesSubplot at 0x7fdf860d5668>


sns.boxplot(x='quality', y='free sulfur dioxide', data=red_wine_df)

<matplotlib.axes._subplots.AxesSubplot at 0x7fdf860545f8>


red_wine_df.columns


sns.boxplot(x='quality', y='fixed acidity', data=red_wine_df)

<matplotlib.axes._subplots.AxesSubplot at 0x7fdf8618f668>


sns.boxplot(x='quality', y='citric acid', data=red_wine_df)

<matplotlib.axes._subplots.AxesSubplot at 0x7fdf85e49ac8>


sns.boxplot(x='quality', y='volatile acidity', data=red_wine_df)

<matplotlib.axes._subplots.AxesSubplot at 0x7fdf85d8eeb8>


red_wine_df.columns

Index(['fixed acidity', 'volatile acidity', 'citric acid', 'residual sugar',
       'chlorides', 'free sulfur dioxide', 'total sulfur dioxide', 'density',
       'pH', 'sulphates', 'alcohol', 'quality'],
      dtype='object')


get_corr('pH', 'citric acid', red_wine_df)


red_wine_df['total acidity'] = (red_wine_df['fixed acidity']+ red_wine_df['citric acid'] + red_wine_df['volatile acidity'])
sns.boxplot(x='quality', y='total acidity', data=red_wine_df,
           showfliers=False)

<matplotlib.axes._subplots.AxesSubplot at 0x7fdf8572b9b0>


sns.regplot(x='pH', y='total acidity', data=red_wine_df)

<matplotlib.axes._subplots.AxesSubplot at 0x7fdf856a1ac8>


g = sns.FacetGrid(red_wine_df, col="quality")
g = g.map(sns.regplot, "total acidity", "pH")


get_corr('total acidity', 'pH', red_wine_df)


g = sns.FacetGrid(red_wine_df, col="quality")
g = g.map(sns.regplot, "free sulfur dioxide", "pH")

	Sno	Age	Height(cm)
count	9.000000	6.000000	7.000000
mean	5.000000	28.166667	154.857143
std	2.738613	2.316607	7.174691
min	1.000000	25.000000	143.000000
25%	3.000000	26.500000	151.000000
50%	5.000000	28.500000	156.000000
75%	7.000000	29.750000	160.000000
max	9.000000	31.000000	163.000000

	Device_name	Device_description	Single-Use
Sno
1	Synringe	Used to inject medicine	True
2	Ventilator	Used to help patients breath	False
3	Surgical Gloves	NaN	True
4	Stethescopes	NaN	NaN
5	Vials container	NaN	NaN

	Sno	Name	Age	Height(cm)	birthday
0	1	John	25.0	160.0	1994-01-01
1	2	Jimmy	26.0	163.0	NaT
2	3	Felicia	28.0	154.0	1995-01-01
3	4	Sophia	NaN	143.0	NaT
4	5	Bob	NaN	NaN	1994-01-01
5	6	Billy	30.0	156.0	1994-01-01
6	7	Kate	31.0	160.0	1990-01-01
7	8	Will	29.0	NaN	1991-07-01
8	9	Scott	NaN	148.0	NaT

	0	1	2	3
0	0.302665	1.693723	-1.706086	-1.159119
1	-0.134841	0.390528	0.166905	0.184502
2	0.807706	0.072960	0.638787	0.329646
3	-0.497104	-0.754070	-0.943406	0.484752
4	-0.116773	1.901755	0.238127	1.996652

		A	B
G1	1	-0.993263	0.196800
	2	-1.136645	0.000366
	3	1.025984	-0.156598
G2	1	-0.031579	0.649826
	2	2.154846	-0.610259
	3	-0.755325	-0.346419

	W	X	Y	Z
A	2.706850	0.628133	0.907969	0.503826
B	0.651118	-0.319318	-0.848077	0.605965
C	-2.018168	0.740122	0.528813	-0.589001
D	0.188695	-0.758872	-0.933237	0.955057
E	0.190794	1.978757	2.605967	0.683509

	W	X	Y	Z
States
CA	2.706850	0.628133	0.907969	0.503826
NY	0.651118	-0.319318	-0.848077	0.605965
WY	-2.018168	0.740122	0.528813	-0.589001
OR	0.188695	-0.758872	-0.933237	0.955057
CO	0.190794	1.978757	2.605967	0.683509

		A	B
Group	Num
G1	1	-0.993263	0.196800
	2	-1.136645	0.000366
	3	1.025984	-0.156598
G2	1	-0.031579	0.649826
	2	2.154846	-0.610259
	3	-0.755325	-0.346419

	Age	Height(cm)
0	20	150
1	21	151
2	24	155
3	24	153
4	28	280
5	26	160
6	19	158
7	22	157
8	26	158
9	24	145
10	21	150
11	19	155
12	22	155
13	28	151
14	29	152
15	6	153
16	100	160
17	25	152
18	25	157
19	28	157
20	31	160

	Survived	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked
PassengerId
1	0	3	Braund, Mr. Owen Harris	male	22.0	1	0	A/5 21171	7.2500	NaN	S
2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	female	38.0	1	0	PC 17599	71.2833	C85	C
3	1	3	Heikkinen, Miss. Laina	female	26.0	0	0	STON/O2. 3101282	7.9250	NaN	S
4	1	1	Futrelle, Mrs. Jacques Heath (Lily May Peel)	female	35.0	1	0	113803	53.1000	C123	S
5	0	3	Allen, Mr. William Henry	male	35.0	0	0	373450	8.0500	NaN	S

	Survived	Pclass	Age	SibSp	Parch	Fare
count	891.000000	891.000000	714.000000	891.000000	891.000000	891.000000
mean	0.383838	2.308642	29.699118	0.523008	0.381594	32.204208
std	0.486592	0.836071	14.526497	1.102743	0.806057	49.693429
min	0.000000	1.000000	0.420000	0.000000	0.000000	0.000000
25%	0.000000	2.000000	20.125000	0.000000	0.000000	7.910400
50%	0.000000	3.000000	28.000000	0.000000	0.000000	14.454200
75%	1.000000	3.000000	38.000000	1.000000	0.000000	31.000000
max	1.000000	3.000000	80.000000	8.000000	6.000000	512.329200

	ID	Name	Sex	Age	Height	Weight	Team	NOC	Games	Year	Season	City	Sport	Event	Medal	region	notes
0	1	A Dijiang	M	24.0	180.0	80.0	China	CHN	1992 Summer	1992	Summer	Barcelona	Basketball	Basketball Men's Basketball	NaN	China	NaN
1	2	A Lamusi	M	23.0	170.0	60.0	China	CHN	2012 Summer	2012	Summer	London	Judo	Judo Men's Extra-Lightweight	NaN	China	NaN
2	3	Gunnar Nielsen Aaby	M	24.0	NaN	NaN	Denmark	DEN	1920 Summer	1920	Summer	Antwerpen	Football	Football Men's Football	NaN	Denmark	NaN
3	4	Edgar Lindenau Aabye	M	34.0	NaN	NaN	Denmark/Sweden	DEN	1900 Summer	1900	Summer	Paris	Tug-Of-War	Tug-Of-War Men's Tug-Of-War	Gold	Denmark	NaN
4	5	Christine Jacoba Aaftink	F	21.0	185.0	82.0	Netherlands	NED	1988 Winter	1988	Winter	Calgary	Speed Skating	Speed Skating Women's 500 metres	NaN	Netherlands	NaN

	ID	Age	Height	Weight	Year
count	271116.000000	261642.000000	210945.000000	208241.000000	271116.000000
mean	68248.954396	25.556898	175.338970	70.702393	1978.378480
std	39022.286345	6.393561	10.518462	14.348020	29.877632
min	1.000000	10.000000	127.000000	25.000000	1896.000000
25%	34643.000000	21.000000	168.000000	60.000000	1960.000000
50%	68205.000000	24.000000	175.000000	70.000000	1988.000000
75%	102097.250000	28.000000	183.000000	79.000000	2002.000000
max	135571.000000	97.000000	226.000000	214.000000	2016.000000

	Name	Type 1	Type 2	Total	HP	Attack	Defense	Sp. Atk	Sp. Def	Speed	Generation	Legendary
#
1	Bulbasaur	Grass	Poison	318	45	49	49	65	65	45	1	False
2	Ivysaur	Grass	Poison	405	60	62	63	80	80	60	1	False
3	Venusaur	Grass	Poison	525	80	82	83	100	100	80	1	False
3	VenusaurMega Venusaur	Grass	Poison	625	80	100	123	122	120	80	1	False
4	Charmander	Fire	NaN	309	39	52	43	60	50	65	1	False

	Total	HP	Attack	Defense	Sp. Atk	Sp. Def	Speed	Generation
count	800.00000	800.000000	800.000000	800.000000	800.000000	800.000000	800.000000	800.00000
mean	435.10250	69.258750	79.001250	73.842500	72.820000	71.902500	68.277500	3.32375
std	119.96304	25.534669	32.457366	31.183501	32.722294	27.828916	29.060474	1.66129
min	180.00000	1.000000	5.000000	5.000000	10.000000	20.000000	5.000000	1.00000
25%	330.00000	50.000000	55.000000	50.000000	49.750000	50.000000	45.000000	2.00000
50%	450.00000	65.000000	75.000000	70.000000	65.000000	70.000000	65.000000	3.00000
75%	515.00000	80.000000	100.000000	90.000000	95.000000	90.000000	90.000000	5.00000
max	780.00000	255.000000	190.000000	230.000000	194.000000	230.000000	180.000000	6.00000

	A	B	C
0	1.0	5.0	1
1	2.0	FILL VALUE	2
2	FILL VALUE	FILL VALUE	3

	Age	Height(cm)
0	20	150
1	21	151
2	24	155
3	24	153
4	28	280
5	26	160
6	19	158
7	22	157
8	26	158
9	24	145
10	21	150
11	19	155
12	22	155
13	28	151
14	29	152
15	6	153
16	100	160
17	25	152
18	25	157
19	28	157
20	31	160

	Name	Type 1	Type 2	Total	HP	Attack	Defense	Sp. Atk	Sp. Def	Speed	Generation	Legendary
#
377	Regirock	Rock	NA	580	80	100	200	50	100	50	3	True
378	Regice	Ice	NA	580	80	50	100	100	200	50	3	True
379	Registeel	Steel	NA	580	80	75	150	75	150	50	3	True
380	Latias	Dragon	Psychic	600	80	80	90	110	130	110	3	True
380	LatiasMega Latias	Dragon	Psychic	700	80	100	120	140	150	110	3	True
381	Latios	Dragon	Psychic	600	80	90	80	130	110	110	3	True
381	LatiosMega Latios	Dragon	Psychic	700	80	130	100	160	120	110	3	True
382	Kyogre	Water	NA	670	100	100	90	150	140	90	3	True
382	KyogrePrimal Kyogre	Water	NA	770	100	150	90	180	160	90	3	True
383	Groudon	Ground	NA	670	100	150	140	100	90	90	3	True
383	GroudonPrimal Groudon	Ground	Fire	770	100	180	160	150	90	90	3	True
384	Rayquaza	Dragon	Flying	680	105	150	90	150	90	95	3	True
384	RayquazaMega Rayquaza	Dragon	Flying	780	105	180	100	180	100	115	3	True
385	Jirachi	Steel	Psychic	600	100	100	100	100	100	100	3	True
386	DeoxysNormal Forme	Psychic	NA	600	50	150	50	150	50	150	3	True
386	DeoxysAttack Forme	Psychic	NA	600	50	180	20	180	20	150	3	True
386	DeoxysDefense Forme	Psychic	NA	600	50	70	160	70	160	90	3	True
386	DeoxysSpeed Forme	Psychic	NA	600	50	95	90	95	90	180	3	True

	Name	Type 1	Type 2	Total	HP	Attack	Defense	Sp. Atk	Sp. Def	Speed	Generation	Legendary
#
494	Victini	Psychic	Fire	600	100	100	100	100	100	100	5	True
638	Cobalion	Steel	Fighting	580	91	90	129	90	72	108	5	True
639	Terrakion	Rock	Fighting	580	91	129	90	72	90	108	5	True
640	Virizion	Grass	Fighting	580	91	90	72	90	129	108	5	True
641	TornadusIncarnate Forme	Flying	NA	580	79	115	70	125	80	111	5	True
641	TornadusTherian Forme	Flying	NA	580	79	100	80	110	90	121	5	True
642	ThundurusIncarnate Forme	Electric	Flying	580	79	115	70	125	80	111	5	True
642	ThundurusTherian Forme	Electric	Flying	580	79	105	70	145	80	101	5	True
643	Reshiram	Dragon	Fire	680	100	120	100	150	120	90	5	True
644	Zekrom	Dragon	Electric	680	100	150	120	120	100	90	5	True
645	LandorusIncarnate Forme	Ground	Flying	600	89	125	90	115	80	101	5	True
645	LandorusTherian Forme	Ground	Flying	600	89	145	90	105	80	91	5	True
646	Kyurem	Dragon	Ice	660	125	130	90	130	90	95	5	True
646	KyuremBlack Kyurem	Dragon	Ice	700	125	170	100	120	90	95	5	True
646	KyuremWhite Kyurem	Dragon	Ice	700	125	120	90	170	100	95	5	True

	fixed acidity	volatile acidity	citric acid	residual sugar	chlorides	free sulfur dioxide	total sulfur dioxide	density	pH	sulphates	alcohol	quality
0	7.4	0.70	0.00	1.9	0.076	11.0	34.0	0.9978	3.51	0.56	9.4	5
1	7.8	0.88	0.00	2.6	0.098	25.0	67.0	0.9968	3.20	0.68	9.8	5
2	7.8	0.76	0.04	2.3	0.092	15.0	54.0	0.9970	3.26	0.65	9.8	5
3	11.2	0.28	0.56	1.9	0.075	17.0	60.0	0.9980	3.16	0.58	9.8	6
4	7.4	0.70	0.00	1.9	0.076	11.0	34.0	0.9978	3.51	0.56	9.4	5

	fixed acidity	volatile acidity	citric acid	residual sugar	chlorides	free sulfur dioxide	total sulfur dioxide	density	pH	sulphates	alcohol	quality
count	1599.000000	1599.000000	1599.000000	1599.000000	1599.000000	1599.000000	1599.000000	1599.000000	1599.000000	1599.000000	1599.000000	1599.000000
mean	8.319637	0.527821	0.270976	2.538806	0.087467	15.874922	46.467792	0.996747	3.311113	0.658149	10.422983	5.636023
std	1.741096	0.179060	0.194801	1.409928	0.047065	10.460157	32.895324	0.001887	0.154386	0.169507	1.065668	0.807569
min	4.600000	0.120000	0.000000	0.900000	0.012000	1.000000	6.000000	0.990070	2.740000	0.330000	8.400000	3.000000
25%	7.100000	0.390000	0.090000	1.900000	0.070000	7.000000	22.000000	0.995600	3.210000	0.550000	9.500000	5.000000
50%	7.900000	0.520000	0.260000	2.200000	0.079000	14.000000	38.000000	0.996750	3.310000	0.620000	10.200000	6.000000
75%	9.200000	0.640000	0.420000	2.600000	0.090000	21.000000	62.000000	0.997835	3.400000	0.730000	11.100000	6.000000
max	15.900000	1.580000	1.000000	15.500000	0.611000	72.000000	289.000000	1.003690	4.010000	2.000000	14.900000	8.000000

Alauddin sabari

Data Preprocessing with pandas.¶

Missing Data Handle¶

Reasons for missing Data¶

df.describe()¶

Since NaN is considered float, the data is converted to float type¶

df.isna() and df.notna()¶

df.isnull()¶

Finding count of missing values in each column¶

Sometimes information for a column is insufficient to assign a value¶

Missing data for datetime¶

DataFrames¶

Selection and Indexing¶

Conditional Selection¶

More Index Details¶

Multi-Index and Index Hierarchy¶

Frequency Histogram¶

Seaborn Documentation : https://seaborn.pydata.org/tutorial/distributions.html¶

Relative Frequency Histogram Plot¶

Density Plot¶

more examples¶

Reasons for missing Data¶

df.describe()¶

Since NaN is considered float, the data is converted to float type¶

df.isna() and df.notna()¶

df.isnull()¶

Finding count of missing values in each column¶

Sometimes information for a column is insufficient to assign a value¶

Missing data for datetime¶

Finding Z-Scores¶

Example for variable¶

Dataset Used : Titanic ( https://www.kaggle.com/c/titanic )¶

Columns¶

Numerical Variables¶

Age and Fare are Continuous Variable¶

Parch and SibSp are Discrete Variables¶

Categorical Variables¶

Nominal Values¶

Oridnal Variable¶

Univariate analysis¶

Dataset : https://www.kaggle.com/heesoo37/120-years-of-olympic-history-athletes-and-results¶

Calculate Skewness¶

Bivariate examples¶

Add a new column - Family size¶

Add a new column - Age Group¶

Multivariate¶

Dataset : https://www.kaggle.com/abcsds/pokemon¶

Dealing with Missing values¶

Store Legendary Pokemon Seperately¶

Pokemon count by Type 1¶

Pokemon count by Type 2¶

We will use Bokeh library for Drawing interactive plots¶

Code modified from : https://bokeh.pydata.org/en/latest/docs/user_guide/interaction/legends.html¶

Red Wine Data Analysis¶

Questions that we can try to answer ?¶

Descriptive Statistics¶

Since there are no null entries, we don't need to deal with missing values.¶

Descriptive Statistics¶

Analysis over Red Wine¶

Let's first check the Quality Column¶

Lets check which of the other columns are highly correlated to Quality¶

Alcohol content is positively skewed¶

Let's see how alcohol varies w.r.t. quality¶

Lets analyze sulphates and quality¶

Lets move on to fixed acidity, volatile acidity and citric acid¶

Trends between other columns¶

Create a new Column Total Acidity¶

Alauddin Sabari¶

alauddin.me¶

Seaborn Documentation : https://seaborn.pydata.org/tutorial/distributions.html ¶

Dataset : https://www.kaggle.com/heesoo37/120-years-of-olympic-history-athletes-and-results ¶

Dataset : https://www.kaggle.com/abcsds/pokemon ¶

Code modified from : https://bokeh.pydata.org/en/latest/docs/user_guide/interaction/legends.html ¶

	Age	Height(cm)
0	20	150
1	21	151
2	24	155
3	24	153
4	28	280
5	26	160
6	19	158
7	22	157
8	26	158
9	24	145
10	21	150
11	19	155
12	22	155
13	28	151
14	29	152
15	6	153
16	100	160
17	25	152
18	25	157
19	28	157
20	31	160